Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add delancy827/solidworks-skills --skill solidworks-automationgit clone --depth 1 https://github.com/delancy827/solidworks-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/delancy827/solidworks-skills/solidworks-automation)<a href="https://agentmods.dev/skills/delancy827/solidworks-skills/solidworks-automation"><img src="https://agentmods.dev/badge/skills/delancy827/solidworks-skills/solidworks-automation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/delancy827/solidworks-skills/solidworks-automation"><img src="https://agentmods.dev/badge/skills/delancy827/solidworks-skills/solidworks-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.34450 |
| Opus 5 | $0.00039 | $0.17225 |
| Sonnet 5 | $0.00016 | $0.06890 |
| Haiku 4.5 | $0.00008 | $0.03445 |
Grade A, and why
solidworks-automation scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**影响**：`curl` 直接下载技能文件会失败。 Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
proc = subprocess.Popen( How it starts
The opening of the file, as written. The whole thing — 3,417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model capability preflight
Before using this skill, identify the active AI model/runtime and state whether it can inspect images/PDF pages directly.
- If the runtime is multimodal or has image/PDF rendering tools, inspect the source drawing visually before extracting dimensions.
- If the runtime is text-only, tell the user before modeling: "This model cannot inspect drawings directly. Please add a multimodal/vision step before this skill, or provide rendered views plus a dimension table." Do not infer unseen geometry from filenames or captions.
- If the runtime can run SolidWorks but cannot inspect screenshots, it may execute scripts only after a vision-capable reviewer or the user validates the drawing interpretation.
- Record the preflight in the output: model/runtime, visual capability, drawing source, and who/what performed visual verification.
Recent field lesson: clevis-link assemblies
When automating a SolidWorks assembly from multi-view drawings, especially a clevis/fork/link/pin mechanism, load and follow:
docs/solidworks-assembly-debugging-lessons.md
If that file is not present in the installed skill package, do not block the task; follow the embedded rules below.
Key rules from that lesson:
- Count repeated part instances from the drawing. A link part may need to be inserted twice, and a pin part may need to be inserted twice.
- Do not replace a missing repeated link with only an extra pin.
- Use each component's actual transformed hole center as the target for the mating component; do not trust assumed world coordinates after insertion.
- Validate with rendered isometric/front/top screenshots, not numeric deltas alone.
- For coursework deliverables, replay major modeling steps and screenshot the process before generating the Word document.
Complex drawing intake rule
Before automating a complex drawing from a PDF/image, build a small dimension ledger:
- Exact: dimensions readable from the drawing and used directly.
- Inferred: values derived from visible dimensions, symmetry, or centerlines.
- Designer choice: missing values chosen conservatively; label them in output.
- Unsupported: cuts, chamfers, slots, threads, or blends that were not executed because the Python COM route is unreliable.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 3,417 lines · 78 tokens per session scan A 92b44307d36d
solidworks-automation is a skill published in the GitHub repository delancy827/solidworks-skills (89 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 34,450 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cad-designer
Design guidance for CAD drawings, including drafting standards, parameter-based design, layers, dimensions, batch output, and review checklists. It focuses on deciding what a drawing should contain before automation creates it.
cad-viewer
Start CAD Viewer and return review links for CAD and robot-description files. Use when visually reviewing .step, .stp, .glb, .stl, .3mf, .dxf, .urdf, .srdf, or .sdf files, especially when handed off from CAD, URDF, SRDF, or SDF generation skills.
solidworks-vibecad
A planning guide for turning natural-language mechanical design requests into structured, parameterized SolidWorks plans that can be reviewed before execution.
add-interfaces
Enrich an existing PartCAD part with connection interfaces and ports (mating metadata) so it can be mated to other parts automatically. Use for /pc:add-interfaces or when the user asks to add interfaces, ports, connectors, or mating information to a part, or to make parts snap/connect/assemble together.
gen-assembly
Generate a PartCAD assembly (an ASSY that composes parts with placement and/or mates) from a description, generating or reusing the component parts and validating the result with the PartCAD CLI. Use for /pc:gen-assembly or when the user asks to generate or create an assembly, mechanism, or multi-part product.
render
Render a PartCAD object or a CAD file to a 2D image - PNG, JPEG, SVG or DXF - from one or many viewing angles (front, back, left, right, top, bottom, iso, or an arbitrary direction), with pc render for an object a package declares or pc adhoc render for a file that belongs to no package. Use for /pc:render or when the…